Responsibilities

• Develop and implement assistant workflows using function and tool calling, returning structured JSON responses.
• Build and package reusable agent skills and lightweight tool adapters for enterprise use.
• Create RAG pipelines, including data ingestion, chunking, embedding, and indexing, with quality and freshness checks.
• Support ChatGPT Enterprise deployments, including workspace setup, SSO/SCIM onboarding, role-based access configuration, and basic custom GPT administration.
• Assist with fine-tuning workflows, including dataset preparation, supervised runs, and performance tracking.
• Implement operability measures—add telemetry for latency, token usage, and cost metrics; write smoke tests and maintain troubleshooting documentation.
• Use frameworks such as LangChain, LangGraph, or Semantic Kernel to build and integrate AI applications.
• Connect assistants with enterprise tools (e.g., Teams, SharePoint) using Copilot Studio connectors or lightweight app integrations.
• Deploy and manage environments via CI/CD pipelines (GitHub Actions, Azure DevOps) and learn Infrastructure as Code (IaC) using Terraform or Bicep.

Requirements

• Graduate in Diploma and specialized in Information Technology/Computer Science/Engineering/Mathematics or relevant.
• Strong programming skills in Python with knowledge of REST APIs, JSON, Git, and basic SQL.
• Academic or internship experience working with OpenAI APIs, including prompting, function calling, RAG, or assistant frameworks.
• Familiarity with CI/CD concepts and enthusiasm to learn IaC, observability, and ChatGPT Enterprise administration.
• Experience with LangChain, LangGraph, or Semantic Kernel.
• Familiarity with Azure Cognitive Search, Redis, or pgvector for vector-based retrieval.
• Exposure to fine-tuning pipelines or Copilot Studio connectors.
• Practitioner-level understanding of major cloud platforms (Azure, AWS, or GCP).